Z.ai: GLM 5.3 Flash Performance
Compare measured TTFT, throughput, uptime, and route health for Z.ai: GLM 5.3 Flash across TrustedRouter providers using metadata-only production probes.
z-ai/glm-5.3-flash
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for Z.ai: GLM 5.3 Flash. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.
| Provider | p50 TTFT | p95 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| tinfoil | 2118 ms | 5053 ms | — | 100.00% | — | 10 |
| near-ai | 4520 ms | 39899 ms | — | 12.50% | — | 24 |
| zai | 4729 ms | 9643 ms | — | 97.14% | — | 35 |
| telnyx | 1327 ms | 3264 ms | — | 100.00% | — | 2 |
| wafer | 1523 ms | 2575 ms | — | 100.00% | — | 7 |
| io-net | 1804 ms | 8004 ms | — | 100.00% | — | 2 |
| makora | 2242 ms | 4064 ms | — | 100.00% | — | 3 |
| parasail | 2446 ms | 3594 ms | — | 100.00% | — | 3 |
| pearl | 2461 ms | 5014 ms | — | 100.00% | — | 7 |
| featherless | 2792 ms | 3096 ms | — | 100.00% | — | 2 |
| friendli | 3165 ms | 6345 ms | — | 100.00% | — | 5 |
| arcee | 3569 ms | 6524 ms | — | 100.00% | — | 3 |
| sail-research | 3667 ms | 15817 ms | — | 75.00% | — | 4 |
| fireworks | 3751 ms | 3751 ms | — | 100.00% | — | 1 |
| engy | 3872 ms | 3872 ms | — | 100.00% | — | 1 |
| baseten | 3879 ms | 3879 ms | — | 100.00% | — | 1 |
| siliconflow | 4589 ms | 4589 ms | — | 100.00% | — | 1 |
| deepinfra | 8086 ms | 8086 ms | — | 100.00% | — | 1 |
| together | — | — | — | 100.00% | — | 2 |
| wandb | — | — | — | 100.00% | — | 1 |
| nvidia-nim | — | — | — | 0.00% | — | 2 |
| phala | — | — | — | 0.00% | — | 6 |
Full provider & model leaderboard.
26 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.